Starts investigating the moment you declare
No cold starts. The moment an incident is declared, Investigations is already correlating signals while your team is still joining the incident channel.
AI SRE
AI SRE that investigates incidents like your most tenured engineer
Investigations starts debugging the moment you declare an incident, connecting telemetry, code changes, and incident history to surface the root cause in minutes.
Meet Investigations, our always-on AI SRE product.
It's like debugging with a teammate who has been in every incident your company has ever had, knows every service you run, and is already working the problem before you've joined the call. Humans and agents, working in lockstep.
See Investigations
Built on the power of Nexus
Investigations runs on Nexus, our production intelligence model. It reasons across your entire environment in real time, so at 3am it can make high-conviction hypotheses on a system it knows inside out.
Learn more about NexusHas access to every piece of relevant context your team has ever produced
Reasons across telemetry, deployments, code, and incident history
Uses an adversarial agent to challenge its own conclusions before sharing
Gets smarter with every incident, the model learns which patterns repeat
AI that is trusted when it matters most
Built for your most critical moments, with the accuracy, transparency, and data isolation enterprise teams require.
Measurably accurate
We backtest against real historical incidents daily, and alert on any degradation before it reaches production.
Evidence-backed audit trail
Every hypothesis links back to its sources and an investigation timeline lets you follow the agent's reasoning.
Your data stays yours
Every customer gets their own instance of Nexus, our production intelligence model, never shared with another customer.
SOC 2 compliant
Code analysis runs in isolated, sandboxed containers torn down after use, and we redact sensitive data before it reaches model providers.
Zero data retention with model providers
We have agreements with our providers so they can't store customer data for logging or training.
Never takes action without you
The only change Investigations can make to your systems is a pull request you review and merge yourself.
Reduce the cost of incidents
The cost of an incident isn't just the downtime. It's the engineering hours, the customer impact, and the context-switching that follows. Investigations, the AI SRE agent, cuts all of it.
- Fewer people pulled in
- More time building
- Less customer impact
Trusted when incidents can't wait
“Investigations drilled down into what changed in that pull request, connected it across multiple repositories, and arrived at the conclusion. Tracing all of those dots as a human would have been nearly impossible.”
James Bourne
Platform Engineer, Contentful
“On live incidents, it cuts out a huge amount of the initial toil in getting to the root cause. People have really got to the point where they can trust what the tool is telling them.”
Russ Williams
Head of Operational Resilience & Incident Management, GoCardless
AI SRE FAQs
So good, you’ll break things on purpose
Ready to put AI to work on your incidents? Book a call with our team today.